Execute browser app actions like opening pages, setting filters, or selecting items; use get_screen to discover available actions and inputs, then receive the action's result.
Run one of the app's actions in the user's browser: open a page, set a filter, select something. get_screen lists the actions and their inputs. Returns what the action returned.
| Name | Required | Description | Default |
|---|---|---|---|
| input | No | ||
| action | Yes |
Changes observed during successful MCP inspections.
v0.4.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that execution happens in the user's live browser and that the action's return value is passed through, but says nothing about side effects, reversibility, permissions, error behavior, or whether actions are destructive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences with the core purpose front-loaded and no filler. The final sentence ('Returns what the action returned') is mildly tautological but still communicates passthrough behavior.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a generic dispatcher with a free-form input object, no annotations, and no output schema, the description covers discovery and return passthrough. It is missing safety, failure-mode, and validation context that an agent would need to invoke arbitrary actions confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the schema documents neither the action string's valid values nor the shape of the arbitrary input object. The description compensates partially by saying get_screen lists actions and their inputs, establishing the action/input relationship, but it leaves the input structure entirely external and does not mention the 80-character action limit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: run one of the app's actions in the user's browser, with concrete examples (open a page, set a filter, select something). It distinguishes itself from get_screen by framing that sibling as the discovery mechanism, though 'one of the app's actions' remains somewhat abstract without knowing the app.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Points the agent to get_screen for the list of actions and their inputs, which implies a prerequisite workflow. However, it never explicitly says to call get_screen first, gives no when-not conditions, and does not contrast with siblings like show_board or describe_data.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.